© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12082
    Prev
    Next
    INDEX
    Explanations

    chop shop, chopping, chopped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĮèĥŀ
    -0.11
    EMENT
    -0.10
    enen
    -0.10
    ement
    -0.09
    zug
    -0.09
    帡
    -0.09
    ally
    -0.09
    ĺ
    -0.09
    éķ¿è¾Ī
    -0.09
    uality
    -0.08
    POSITIVE LOGITS
    sticks
    0.12
    äºĽä»Ģä¹Ī
    0.10
    pearance
    0.09
    媳
    0.09
    åĬ¡å®ŀ
    0.09
    PING
    0.09
    ç¹ģçIJIJ
    0.09
    tures
    0.09
    æİī
    0.09
    apter
    0.09
    Activations Density 0.006%

    No Known Activations